Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    survey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    平均每
    -0.07
    (edge
    -0.06
    secutive
    -0.06
    encent
    -0.06
    atatype
    -0.06
     seamless
    -0.06
    紧凑
    -0.06
    惊艳
    -0.06
     transforms
    -0.06
    ль
    -0.06
    POSITIVE LOGITS
     >(
    0.07
    Bear
    0.06
    樱花
    0.06
    	window
    0.06
     כבר
    0.06
    صحة
    0.06
     ży
    0.06
    时空
    0.06
    _Context
    0.06
     applicable
    0.06
    Act Density 0.039%

    No Known Activations